coherra_repair_safe

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully carries the behavioral disclosure burden. It explains exactly what gets auto-applied (stale → archive, duplicate → merge), explicitly warns that contradictions are never auto-resolved, and provides the return shape. The tool's mutating behavior is transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well-structured, with a front-loaded summary sentence, bulleted behavior details, an explicit exclusion, and a return format. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool, this is complete: it names the source of repairs, defines what counts as safe, identifies the boundary case, and documents the return value. Since an output schema exists, the description does not need to further detail result fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. There is no parameter information to add, and the description appropriately focuses on the implicit state input ('the last audit') rather than parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb-resource pairing: 'Batch-apply all safe repairs from the last audit.' It clearly distinguishes this tool from coherra_repair by stating that contradictions are never auto-resolved and require the manual repair tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states what this tool handles (safe repairs: stale and duplicate) and what it does not handle (contradictions), directing the agent to coherra_repair with keep_a / keep_b / merge_manual for those cases. This gives clear when-to-use and when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.